Files
claude-engineering-plugin/plugins/compound-engineering/skills/ce-review/references/persona-catalog.md
John Lamb fe3b1eee16 Merge upstream v2.67.0 with fork customizations preserved
Synced 79 commits from EveryInc/compound-engineering-plugin upstream while
preserving fork-specific customizations (Python/FastAPI pivot, Zoominfo-internal
review agents, deploy-wiring operational lessons, custom personas).

## Triage decisions (15 conflicts resolved)

Keep deleted (7) -- fork already removed these in prior cleanups:
- agents/design/{design-implementation-reviewer,design-iterator,figma-design-sync}
  (no fork successor; backend-Python focus doesn't need UI/Figma agents)
- agents/docs/ankane-readme-writer (replaced by python-package-readme-writer)
- agents/review/{data-migration-expert,performance-oracle,security-sentinel}
  (replaced by *-reviewer naming convention: data-migrations-reviewer,
  performance-reviewer, security-reviewer)

Keep local (1):
- agents/workflow/lint.md (Python tooling: ruff/mypy/djlint/bandit; upstream
  deleted the file). Fixed pre-existing duplicate "2." numbering bug.

Restore from upstream (1):
- agents/review/data-integrity-guardian.md (kept for GDPR/CCPA privacy
  compliance angle not covered by data-migrations-reviewer)

Merge both (6) -- upstream structural wins layered with fork intent:
- agents/research/best-practices-researcher.md (upstream <examples> removal +
  fork's Rails/Ruby -> Python/FastAPI translations)
- skills/ce-brainstorm/SKILL.md (universal-brainstorming routing + Slack
  context + non-obvious angles + fork's Deploy wiring flag)
- skills/ce-plan/SKILL.md (universal-planning routing + planning-bootstrap +
  fork's two Deploy wiring check bullets)
- skills/ce-review/SKILL.md (Run ID, model tiering haiku->sonnet, compact-JSON
  artifact contract, file-type awareness, cli-readiness-reviewer + fork's
  zip-agent-validator, design-conformance-reviewer, Stage 6 Zip Agent
  Validation)
- skills/ce-review/references/persona-catalog.md (cli-readiness row + adversarial
  refinement + fork's Language & Framework Conditional layer; 22 personas total)
- skills/ce-work/SKILL.md (Parallel Safety Check, parallel-subagent constraints,
  Phase 3-4 compression + fork's deploy-values self-review row, with duplicate
  checklist bullet collapsed to single occurrence)

## Auto-applied (no triage needed)

- 225 remote-only files: accepted as-is (new docs, brainstorms, plans,
  upstream skills, tests, scripts)
- 70 local-only files: 46 preserved as-is (kieran-python, tiangolo-fastapi,
  zip-agent-validator, design-conformance-reviewer, essay/proof commands,
  excalidraw-png-export, etc.); 24 stayed deleted (dhh-rails-style,
  andrew-kane-gem-writer, dspy-ruby Ruby skills no longer needed)

## README updated

- Removed Design section (3 deleted agents)
- Removed deleted Review entries (data-migration-expert, dhh-rails-reviewer,
  kieran-rails-reviewer, performance-oracle, security-sentinel)
- Added new Review entries: design-conformance-reviewer, previous-comments-reviewer,
  tiangolo-fastapi-reviewer, zip-agent-validator
- Workflow: added lint
- Docs: replaced ankane-readme-writer with python-package-readme-writer

## Known issues (not introduced by merge decisions)

- 9 detect-project-type.sh tests fail on macOS bash 3.2 (script uses
  `declare -A` which requires bash 4+). Upstream regression in commit 070092d
  (#568). Resolution: install bash 4+ via `brew install bash` locally;
  upstream fix tracked separately.
- 2 review-skill-contract tests reference deleted agents (dhh-rails-reviewer,
  data-migration-expert). Pre-existing fork inconsistency, not new.

bun run release:validate: passes (46 agents, 51 skills, 0 MCP servers)
2026-04-17 17:24:41 -05:00

8.1 KiB

Persona Catalog

22 reviewer personas organized into always-on, cross-cutting conditional, stack-specific conditional, and language/framework conditional layers, plus CE-specific agents. The orchestrator uses this catalog to select which reviewers to spawn for each review.

Always-on (4 personas + 2 CE agents)

Spawned on every review regardless of diff content.

Persona agents (structured JSON output):

Persona Agent Focus
correctness compound-engineering:review:correctness-reviewer Logic errors, edge cases, state bugs, error propagation, intent compliance
testing compound-engineering:review:testing-reviewer Coverage gaps, weak assertions, brittle tests, missing edge case tests
maintainability compound-engineering:review:maintainability-reviewer Coupling, complexity, naming, dead code, premature abstraction
project-standards compound-engineering:review:project-standards-reviewer CLAUDE.md and AGENTS.md compliance -- frontmatter, references, naming, cross-platform portability, tool selection

CE agents (unstructured output, synthesized separately):

Agent Focus
compound-engineering:review:agent-native-reviewer Verify new features are agent-accessible
compound-engineering:research:learnings-researcher Search docs/solutions/ for past issues related to this PR's modules and patterns

Conditional (8 personas)

Spawned when the orchestrator identifies relevant patterns in the diff. The orchestrator reads the full diff and reasons about selection -- this is agent judgment, not keyword matching.

Persona Agent Select when diff touches...
security compound-engineering:review:security-reviewer Auth middleware, public endpoints, user input handling, permission checks, secrets management
performance compound-engineering:review:performance-reviewer Database queries, ORM calls, loop-heavy data transforms, caching layers, async/concurrent code
api-contract compound-engineering:review:api-contract-reviewer Route definitions, serializer/interface changes, event schemas, exported type signatures, API versioning
data-migrations compound-engineering:review:data-migrations-reviewer Migration files, schema changes, backfill scripts, data transformations
reliability compound-engineering:review:reliability-reviewer Error handling, retry logic, circuit breakers, timeouts, background jobs, async handlers, health checks
adversarial compound-engineering:review:adversarial-reviewer Diff has >=50 changed lines of executable code (not prose/instruction Markdown, JSON schemas, or config), OR touches auth, payments, data mutations, external API integrations, or other high-risk domains regardless of file type
cli-readiness compound-engineering:review:cli-readiness-reviewer CLI command definitions, argument parsing, CLI framework usage, command handler implementations
previous-comments compound-engineering:review:previous-comments-reviewer PR-only. Reviewing a PR that has existing review comments or review threads from prior review rounds. Skip entirely when no PR metadata was gathered in Stage 1.

Stack-Specific Conditional (5 personas)

These reviewers keep their original opinionated lens. They are additive with the cross-cutting personas above, not replacements for them.

Persona Agent Select when diff touches...
dhh-rails compound-engineering:review:dhh-rails-reviewer Rails architecture, service objects, authentication/session choices, Hotwire-vs-SPA boundaries, or abstractions that may fight Rails conventions
kieran-rails compound-engineering:review:kieran-rails-reviewer Rails controllers, models, views, jobs, components, routes, or other application-layer Ruby code where clarity and conventions matter
kieran-python compound-engineering:review:kieran-python-reviewer Python modules, endpoints, services, scripts, or typed domain code
kieran-typescript compound-engineering:review:kieran-typescript-reviewer TypeScript components, services, hooks, utilities, or shared types
julik-frontend-races compound-engineering:review:julik-frontend-races-reviewer Stimulus/Turbo controllers, DOM event wiring, timers, async UI flows, animations, or frontend state transitions with race potential

Language & Framework Conditional (5 personas)

Spawned when the orchestrator identifies language or framework-specific patterns in the diff. These provide deeper domain expertise than the general-purpose personas above.

Persona Agent Select when diff touches...
python-quality compound-engineering:review:kieran-python-reviewer Python files, FastAPI routes, Pydantic models, async/await patterns, SQLAlchemy usage
fastapi-philosophy compound-engineering:review:tiangolo-fastapi-reviewer FastAPI application code, dependency injection, response models, middleware, OpenAPI schemas
typescript-quality compound-engineering:review:kieran-typescript-reviewer TypeScript files, React components, type definitions, generic patterns
frontend-races compound-engineering:review:julik-frontend-races-reviewer Frontend JavaScript, Stimulus controllers, event listeners, async UI code, animations, DOM lifecycle
architecture compound-engineering:review:architecture-strategist New services, module boundaries, dependency graphs, API layer changes, package structure

CE Conditional Agents (design, migration & external review)

These CE-native agents provide specialized analysis beyond what the persona agents cover. Spawn them when the diff includes database migrations, schema.rb, data backfills, design documents, or when the PR originates from specific platforms.

Agent Focus Select when...
compound-engineering:review:design-conformance-reviewer Surfaces deviations between the diff and the repo's design docs or implementation plan The repo contains design documents (docs/, docs/design/, docs/architecture/, docs/specs/) or an active plan matching the current branch
compound-engineering:review:schema-drift-detector Cross-references schema.rb changes against included migrations to catch unrelated drift The diff includes migration files or schema.rb
compound-engineering:review:deployment-verification-agent Produces Go/No-Go deployment checklist with SQL verification queries and rollback procedures The diff includes migration files, schema.rb, or data backfills
compound-engineering:review:zip-agent-validator Pressure-tests zip-agent review comments for validity against full codebase context The PR URL contains git.zoominfo.com

Selection rules

  1. Always spawn all 4 always-on personas plus the 2 CE always-on agents.
  2. For each cross-cutting conditional persona, the orchestrator reads the diff and decides whether the persona's domain is relevant. This is a judgment call, not a keyword match.
  3. For each stack-specific conditional persona, use file types and changed patterns as a starting point, then decide whether the diff actually introduces meaningful work for that reviewer. Do not spawn language-specific reviewers just because one config or generated file happens to match the extension.
  4. For each language/framework conditional persona, check whether the diff touches language or framework-specific patterns that warrant deeper domain expertise. These are additive with stack-specific personas, not replacements.
  5. For CE conditional agents, spawn when applicable: migration files (db/migrate/*.rb, db/schema.rb) or data backfill scripts trigger schema-drift-detector and deployment-verification-agent; design documents or active plans trigger design-conformance-reviewer; PR URLs containing git.zoominfo.com trigger zip-agent-validator.
  6. Announce the team before spawning with a one-line justification per conditional reviewer selected.